CN113593548A - Awakening method and device of intelligent equipment, storage medium and electronic device - Google Patents
Awakening method and device of intelligent equipment, storage medium and electronic device Download PDFInfo
- Publication number
- CN113593548A CN113593548A CN202110725401.3A CN202110725401A CN113593548A CN 113593548 A CN113593548 A CN 113593548A CN 202110725401 A CN202110725401 A CN 202110725401A CN 113593548 A CN113593548 A CN 113593548A
- Authority
- CN
- China
- Prior art keywords
- target
- wake
- candidate
- angle
- devices
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000002618 waking effect Effects 0.000 claims abstract description 8
- 239000002245 particle Substances 0.000 claims description 66
- 230000006870 function Effects 0.000 claims description 35
- 238000010845 search algorithm Methods 0.000 claims description 26
- 230000001629 suppression Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 11
- 238000007476 Maximum Likelihood Methods 0.000 claims description 7
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 12
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L2021/02082—Noise filtering the noise being echo, reverberation of the speech
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method and a device for waking up intelligent equipment, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring a smart device which is allowed to be awakened by an awakening signal from a plurality of smart devices as a candidate device; determining a target awakening angle and target awakening energy corresponding to each candidate device in the plurality of candidate devices under the condition that the number of the candidate devices is multiple; and determining a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is used for responding to the wake-up signal. By adopting the technical scheme, the problems that in the related technology, the accuracy of the intelligent equipment for responding to the awakening instruction is low and the like are solved.
Description
Technical Field
The invention relates to the field of communication, in particular to a method and a device for waking up intelligent equipment, a storage medium and an electronic device.
Background
With the development of computer performance, artificial intelligence begins to show its advantages in various aspects, and people gradually experience the charm of the interconnection of intelligent science and technology and everything. In an intelligent home scene, a plurality of devices with voice interaction functions, such as a television, a sound box, an air conditioner and the like, are simultaneously arranged, and after a user sends a wake-up instruction, only one device may be required to respond. In the current solution, considering the location of the user relative to the device, assuming that the user sending the wake-up command is within a preset range of the device a, even if there is another device B closer to the user and the user actually wants to wake up the device B, the device a still responds preferentially. This results in the device responding to the user wake-up instruction not being the device that the user really wants to wake up.
Aiming at the problems that the accuracy of the intelligent equipment for responding to the awakening instruction is low and the like in the related technology, an effective solution is not provided.
Disclosure of Invention
The embodiment of the invention provides a method and a device for waking up intelligent equipment, a storage medium and an electronic device, which are used for at least solving the problems that in the related art, the accuracy of the intelligent equipment for responding to a wake-up instruction is low and the like.
According to an embodiment of the present invention, a method for waking up an intelligent device is provided, including: acquiring a smart device which is allowed to be awakened by an awakening signal from a plurality of smart devices as candidate devices, wherein the plurality of smart devices are devices which detect the awakening signal in a target scene; determining a target wake-up angle and a target wake-up energy corresponding to each candidate device in the plurality of candidate devices when the number of the candidate devices is multiple, wherein the target wake-up angle is used for indicating a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used for indicating an energy of the wake-up signal received by each candidate device; and determining a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is used for responding to the wake-up signal.
In an exemplary embodiment, the determining a target device from the plurality of candidate devices according to the target wake-up angle and the target wake-up energy includes: determining candidate equipment with a target awakening angle falling into an angle range as the target equipment; and when the target awakening angles corresponding to the candidate devices do not fall into the angle range, determining the candidate device with the maximum target awakening energy as the target device.
In an exemplary embodiment, determining a target wake-up angle corresponding to each candidate device of the plurality of candidate devices includes: constructing a search function of the wake-up angle variable of each candidate device based on the wake-up signal and the wake-up angle variable of each candidate device; and carrying out optimization search on the search function to obtain an optimal solution of the awakening angle variable of each candidate device as a target awakening angle corresponding to each candidate device.
In an exemplary embodiment, constructing a search function of the wake-up angle variable of each candidate device based on the wake-up signal and the wake-up angle variable of each candidate device includes: constructing a covariance matrix of wake-up angle variables for each candidate device based on the wake-up signals; constructing a direction derivative of the wake-up angle variable of each candidate device based on the wake-up angle variable of each candidate device; constructing a maximum likelihood function of a wake-up angle variable of the each candidate device as the search function based on the covariance matrix and the direction vector.
In an exemplary embodiment, performing an optimization search on the search function to obtain an optimal solution of the wake-up angle variable of each candidate device as the target wake-up angle corresponding to each candidate device includes: initializing search parameters in an optimized search algorithm to obtain target search parameters, wherein the search parameters comprise: the number of particles, the positions of the particles, the number of iterations, the position range of each particle, the maximum speed of each particle and a learning factor; and executing the optimized search algorithm on the search function by adopting the target search parameter and the linear decreasing inertial weight to obtain an optimal solution of the wake-up angle variable of each candidate device as a target wake-up angle corresponding to each candidate device.
In an exemplary embodiment, initializing search parameters in an optimized search algorithm to obtain target search parameters includes: initializing the number of particles, the iteration times, the maximum speed of each particle and the learning factor to obtain a target particle number, a target iteration time, a target maximum speed and a target learning factor, wherein the target particle number, the target iteration time, the target maximum speed and the target learning factor are used for enabling the calculation amount of the optimized search algorithm to be minimum when the accuracy of the optimized search algorithm reaches an accuracy threshold; initializing the position range of each particle according to the microphone array arrangement mode of each candidate device to obtain a target position range; initializing the particle position by using a historical optimal solution to obtain a target particle position, wherein the target search parameter comprises: the target particle number, the target iteration number, the target maximum speed, the target learning factor, the target position range and the target particle position.
In an exemplary embodiment, determining a target wake-up energy corresponding to each candidate device of the plurality of candidate devices includes: calculating the energy sum of each candidate device in the frequency range of the wake-up signal; and determining the energy sum as a target wake-up energy corresponding to each candidate device.
In one exemplary embodiment, acquiring a smart device that is allowed to be woken up by a wake-up signal from a plurality of smart devices as a candidate device includes: performing echo cancellation operation and/or noise cancellation operation on the voice signal received by each intelligent device to obtain the wake-up signal, wherein the noise cancellation operation includes at least one of the following operations: stationary noise suppression, reverberation suppression, non-stationary noise suppression; performing awakening judgment on each intelligent device based on the awakening signal; and determining the intelligent equipment which is successfully awakened and distinguished in the plurality of intelligent equipment as the candidate equipment.
According to another embodiment of the present invention, there is also provided a wake-up apparatus for an intelligent device, including: the device comprises an acquisition module, a judgment module and a control module, wherein the acquisition module is used for acquiring intelligent devices which are allowed to be awakened by an awakening signal from a plurality of intelligent devices as candidate devices, and the intelligent devices are devices which detect the awakening signal in a target scene; a first determining module, configured to determine, when the number of the candidate devices is multiple, a target wake-up angle and a target wake-up energy corresponding to each candidate device in the multiple candidate devices, where the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used to indicate an energy at which the wake-up signal is received by each candidate device; a second determining module, configured to determine a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, where the target device is configured to respond to the wake-up signal.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the above-mentioned wake-up method of the smart device when running.
According to another aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the wake-up method of the intelligent device through the computer program.
In the embodiment of the invention, intelligent devices which are allowed to be awakened by an awakening signal are obtained from a plurality of intelligent devices as candidate devices, wherein the plurality of intelligent devices are devices which detect the awakening signal in a target scene; under the condition that the number of the candidate devices is multiple, determining a target wake-up angle and a target wake-up energy corresponding to each candidate device in the multiple candidate devices, wherein the target wake-up angle is used for indicating the direction of the sound source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used for indicating the energy of the wake-up signal received by each candidate device; and determining target equipment from the candidate equipment according to the target awakening angle and the target awakening energy, wherein the target equipment is used for responding to the awakening signal, namely when the equipment which detects the awakening signal in the target scene is a plurality of intelligent equipment, the intelligent equipment which is allowed to be awakened by the awakening signal is obtained as the candidate equipment, when the number of the candidate equipment is a plurality of equipment, the target awakening angle and the target awakening energy which correspond to each candidate equipment are determined, and then the target equipment which is used for responding to the awakening signal is determined according to the target awakening angle and the target awakening energy. By adopting the technical scheme, the problems that in the related technology, the accuracy of the intelligent equipment for responding to the awakening instruction is low and the like are solved, and the technical effect of improving the accuracy of the intelligent equipment for responding to the awakening instruction is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a block diagram of a hardware structure of a computer terminal of a wake-up method for an intelligent device according to an embodiment of the present invention;
FIG. 2 is a flow chart of a wake-up method of a smart device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a wake-up method of a smart device according to an embodiment of the invention;
fig. 4 is a block diagram of a wake-up apparatus of a smart device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The method provided by the embodiment of the invention can be executed in a computer terminal, a computer terminal or a similar arithmetic device. Taking an example of the operation on a computer terminal, fig. 1 is a hardware structure block diagram of a computer terminal of the wake-up method of an intelligent device according to the embodiment of the present invention. As shown in fig. 1, the computer terminal may include one or more (only one shown in fig. 1) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and in an exemplary embodiment, may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the computer terminal. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration with equivalent functionality to that shown in FIG. 1 or with more functionality than that shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to the wake-up method of the smart device in the embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to execute various functional applications and data processing, i.e., to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In this embodiment, a wake-up method for an intelligent device is provided, which is applied to the computer terminal, and fig. 2 is a flowchart of the wake-up method for the intelligent device according to the embodiment of the present invention, where the flowchart includes the following steps:
step S202, acquiring intelligent devices which are allowed to be awakened by an awakening signal from a plurality of intelligent devices as candidate devices, wherein the intelligent devices are the devices which detect the awakening signal in a target scene;
step S204, determining a target wake-up angle and a target wake-up energy corresponding to each candidate device in the plurality of candidate devices when the number of the candidate devices is multiple, where the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used to indicate an energy of the wake-up signal received by each candidate device;
step S206, determining a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is configured to respond to the wake-up signal.
Through the steps, when the device which detects the wake-up signal in the target scene is a plurality of intelligent devices, the intelligent devices which are allowed to be wakened by the wake-up signal are obtained as candidate devices, when the number of the candidate devices is a plurality, the target wake-up angle and the target wake-up energy corresponding to each candidate device are determined, and then the target device used for responding to the wake-up signal is determined according to the target wake-up angle and the target wake-up energy. By adopting the technical scheme, the problems that in the related technology, the accuracy of the intelligent equipment for responding to the awakening instruction is low and the like are solved, and the technical effect of improving the accuracy of the intelligent equipment for responding to the awakening instruction is achieved.
In the technical solution provided in step S202, the plurality of smart devices are devices that detect the wake-up signal in the target scene, for example: television, set-top box, mobile phone, sound box, air conditioner, oven, steam box, frying pan, microwave oven, etc.
Optionally, in this embodiment, the wake-up signal may be, but is not limited to, wake-up information extracted from a voice signal sent by a user for wake-up determination, such as: the voice signal sent by the user is processed in a series of ways to obtain a wake-up signal, and a wake-up instruction, such as a wake-up keyword, can be extracted from the wake-up signal. The plurality of intelligent devices may be, but not limited to, devices that receive the voice signal and extract the wake-up keyword in the target scene, and the intelligent device that is allowed to be woken up by the wake-up signal may be, but not limited to, devices that are allowed to be woken up using the same wake-up keyword in the target scene.
Optionally, in this embodiment, the target scenario may include, but is not limited to, any type of scenario that allows intelligent control, such as: home, garage, office, classroom, teaching building, laboratory, etc.
In an exemplary embodiment, the smart device that is allowed to wake up by the wake-up signal may be obtained as a candidate device from a plurality of smart devices, but is not limited to: performing echo cancellation operation and/or noise cancellation operation on the voice signal received by each intelligent device to obtain a wake-up signal, wherein the noise cancellation operation includes at least one of the following operations: stationary noise suppression, reverberation suppression, non-stationary noise suppression; awakening and distinguishing each intelligent device based on the awakening signal; and determining the intelligent equipment which is successfully awakened and distinguished from the plurality of intelligent equipment as candidate equipment.
Optionally, in this embodiment, for the device with the self-broadcasting function in the smart device, an echo cancellation operation (AEC) may be performed first, and the echo cancellation operation may be, but is not limited to, adopting the NLMS dual-filter method.
Optionally, in the present embodiment, the noise cancellation operation may include, but is not limited to, at least one of: stationary noise suppression, reverberation suppression, non-stationary noise suppression. That is, one or more noise cancellation operations may be performed on the speech signal or the speech signal after the echo cancellation operation is performed, as required. The noise cancellation operation may be, but is not limited to, processing in the stft domain.
Alternatively, in this embodiment, the operation process of stationary noise suppression may be, but is not limited to, first estimating the noise spectrum by using the minimum tracking method IMCRA, and then obtaining the gain value G of stationary noise suppression by using the optimal modified log spectrum amplitude estimation OMLSAn(f)。
Optionally, in this embodiment, the operation process of reverberation suppression may be, but is not limited to, using CDR estimation, assuming that the noise field is a scattering noise field, calculating CDR once for each group of microphone pairs, and performing weighted average on each group to obtain CDR (f) to obtain a gain value G of reverberation suppressionr(f)。
Optionally, in this embodiment, the operation procedure of non-stationary noise suppression may be, but is not limited to, using a linear filter, assuming that the length of the wakeup word is at most 800ms, and adapting the data with the wakeup word at the current time of noise cancellation by using the filter information updated by the data before 800 ms. Obtaining a signal X through a linear filterw(f) Then, the gain value G for non-stationary noise suppression can be obtaineds(m, f). Wherein the content of the first and second substances,
in the noise elimination operation, the calculation amount of the noise elimination operation process is controlled, so that the calculation amount of the whole awakening process of the intelligent device is reduced, and the calculation speed and efficiency of the awakening process of the intelligent device are improved.
Optionally, in this embodiment, the wake-up signal obtained after the echo cancellation operation and/or the noise cancellation operation is converted into a time domain through istft, and then wake-up discrimination is performed in an AGC manner, so that an intelligent device that is successfully wake-up discriminated among the plurality of intelligent devices is determined as a candidate device.
Optionally, in this embodiment, in consideration of the influence of noise, late reverberation, and non-stationary noise, a method with a small calculation amount is adopted, and a good direction wake-up effect can be obtained on a device with poor performance.
In the technical solution provided in step S204 above, the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device. The target wake angle may be determined, but is not limited to, using a DOA estimation algorithm. The target wake-up energy is used to indicate the energy at which each candidate device receives the wake-up signal. The target wake-up energy may be determined, but is not limited to, using an energy estimation algorithm.
In an exemplary embodiment, the target wake-up angle corresponding to each candidate device of the plurality of candidate devices may be determined, but is not limited to, by: constructing a search function of the wake-up angle variable of each candidate device based on the wake-up signal and the wake-up angle variable of each candidate device; and carrying out optimization search on the search function to obtain the optimal solution of the awakening angle variable of each candidate device as the target awakening angle corresponding to each candidate device.
Optionally, in this embodiment, the target wake-up angle corresponding to each candidate device may be determined, but is not limited to, by constructing a search function and performing an optimized search on the search function.
Optionally, in this embodiment, the search function of the wake angle variable may be, but is not limited to, in the form of a function of a maximum likelihood function.
In an exemplary embodiment, the search function for the wake angle variable of each candidate device may be constructed based on the wake signal and the wake angle variable of each candidate device in, but not limited to, the following manner: constructing a covariance matrix of a wake-up angle variable of each candidate device based on the wake-up signal; constructing a direction derivative of the wake-up angle variable of each candidate device based on the wake-up angle variable of each candidate device; a maximum likelihood function of the wake-up angle variable for each candidate device is constructed as a search function based on the covariance matrix and the direction vector.
Optionally, in this embodiment, the maximum likelihood function of the wake angle variable may be, but is not limited to:
where PA (θ, f) is the direction derivative of the wake angle variable: PA (theta, f) ═ e-j*2πf*d/c. d is the distance of the sound source relative to the origin at the angle θ. Rxx (f) ═ X (f) ×*(f) Is a covariance matrix. X (f) is the microphone array signal.
Alternatively, in the present embodiment, but not limited to, by Xc(m，f)＝X(m，f)*Gn(f)Gr(f)*Gs(m, f) to obtain a covariance matrix rxx (f) ═ Xc(f)*Xc *(f) In that respect Where X (m, f) is the frequency domain signal of each microphone array.
Optionally, in this embodiment, during the echo cancellation operation, each microphone is defaulted to be AEC, and when the number of microphones is large, the amount of calculation increases, and if the amount of calculation needs to be simplified, because 1 path of the target channel of the linear filter is used, and the reference channel is another 1 path of the signal subjected to echo cancellation, AEC may be used in two paths only. If the AEC does two passes only, then the gain value of the echo cancellation operation needs to be calculated
When solving the covariance matrix, the user needs to multiply Ge(m, f) to give the final Xc(m，f)。
In an exemplary embodiment, the search function may be optimally searched, but not limited to, by the following means, to obtain an optimal solution of the wake-up angle variable of each candidate device as the target wake-up angle corresponding to each candidate device: initializing search parameters in an optimized search algorithm to obtain target search parameters, wherein the search parameters comprise: the number of particles, the positions of the particles, the number of iterations, the position range of each particle, the maximum speed of each particle and a learning factor; and executing an optimization search algorithm on the search function by adopting the target search parameters and the linear decreasing inertial weight to obtain an optimal solution of the awakening angle variable of each candidate device as a target awakening angle corresponding to each candidate device.
Optionally, in this embodiment, the search parameters in the optimized search algorithm may include, but are not limited to: the number of particles, the position of the particles, the number of iterations, the range of positions of each particle, the maximum velocity and learning factor of each particle, and the like.
Optionally, in the present embodiment, the optimization search algorithm may include, but is not limited to, a particle swarm optimization algorithm, and the like.
In an exemplary embodiment, the search parameters in the optimized search algorithm may be initialized, without limitation, to obtain the target search parameters by: initializing the number of particles, the number of iterations, the maximum speed of each particle and a learning factor to obtain the number of target particles, the number of target iterations, the maximum speed of a target and the learning factor of the target, wherein the number of target particles, the number of target iterations, the maximum speed of the target and the learning factor of the target are used for enabling the accuracy of the optimized search algorithm to reach an accuracy threshold value and simultaneously enabling the calculated amount of the optimized search algorithm to be minimum; initializing the position range of each particle according to the microphone array arrangement mode of each candidate device to obtain a target position range; initializing the particle position by using a historical optimal solution to obtain a target particle position, wherein the target search parameter comprises: the number of target particles, the number of target iterations, the maximum speed of the target, the target learning factor, the target position range and the target particle position.
Optionally, in this embodiment, in order to minimize the calculation amount of the optimized search algorithm while the accuracy of the optimized search algorithm reaches the accuracy threshold, the number of particles, the number of iterations, the maximum speed of each particle, and the value of the learning factor may be subjected to a trade-off, for example: the number of target particles is 2, the target iteration times is 10, the target maximum speed is not more than pi/2, and the target learning factor is 2, so that the calculation amount of the optimized search algorithm is minimum while the accuracy of the optimized search algorithm reaches the accuracy threshold.
Optionally, in this embodiment, the target position range may be determined according to, but not limited to, the microphone array arrangement of each candidate device, such as: for a linearly arranged microphone array, the range of positions of each particle may be, but is not limited to, [0, π ].
Optionally, in this embodiment, initializing the particle position using the historical optimal solution to obtain the target particle position can accelerate convergence of the optimization search algorithm.
Through the process, the optimal solution of the equation is rapidly solved through particle swarm optimization by adopting a maximum likelihood estimation method. On one hand, array information is fully utilized, and the influence of reverberation, noise and non-stationary noise is considered when a covariance matrix is solved, so that the algorithm robustness is greatly improved; on the other hand, by utilizing particle swarm optimization, 2 particles are used and 10 iterations are carried out, the optimal solution can be stably obtained, the full-space angle search is avoided, and the calculated amount is greatly reduced.
In an exemplary embodiment, the target wake-up energy corresponding to each candidate device of the plurality of candidate devices may be determined, but is not limited to, by: calculating the energy sum of each candidate device in the frequency range of the wake-up signal; and determining the energy sum as a target wake-up energy corresponding to each candidate device.
Optionally, in this embodiment, the target wake-up energy corresponding to each candidate device may be, but is not limited to be, expressed as
Xw(f) Is a wake-up signal obtained after an echo cancellation operation and/or a noise cancellation operation.
In the technical solution provided in step S206, a device more suitable for the user 'S expectation can be determined from the multiple candidate devices as the target device to respond to the user' S wake-up signal according to the target wake-up angle and the target wake-up energy.
In an exemplary embodiment, the target device may be determined from the plurality of candidate devices according to the target wake-up angle and the target wake-up energy by, but not limited to: determining candidate equipment with a target awakening angle falling into an angle range as the target equipment; and when the target awakening angles corresponding to the candidate devices do not fall into the angle range, determining the candidate device with the maximum target awakening energy as the target device.
Optionally, in this embodiment, each smart device corresponds to an angle range allowing responding to wake-up, such as: the wake-up signal may be set to be issued towards the smart device to allow the smart device to respond.
Optionally, in this embodiment, if the number of candidate devices whose corresponding target wake-up angles fall within the corresponding angle range is not unique, the candidate device whose corresponding target wake-up energy is the largest may also be determined as the target device.
Optionally, in this embodiment, if none of the target wake-up angles corresponding to the multiple candidate devices falls within the corresponding angle range, the target device is determined according to the target wake-up energy corresponding to the candidate device, for example: and determining the candidate device with the maximum target wake-up energy in the plurality of candidate devices as the target device.
Optionally, in this embodiment, first, whether a user sending an awake signal is within a preset angle range of a certain device is determined by determining whether the corresponding target awake angle falls within the corresponding angle range, and if so, the device responds preferentially; otherwise, comparing the target wake-up energy of each device, and responding preferentially by the device with the maximum target wake-up energy.
Optionally, in this embodiment, for each microphone array of each candidate device, if the microphone sensitivity and gain are the same, no energy calibration is needed; if the sensitivity, gain and model of each microphone array are not consistent, energy calibration is needed before energy comparison.
In order to better understand the process of the wake-up method of the intelligent device, the following describes an implementation method flow of the wake-up process of the intelligent device with reference to an optional embodiment, but the implementation method flow is not limited to the technical solution of the embodiment of the present invention.
In this embodiment, a wake-up method of a smart device is provided, and fig. 3 is a schematic diagram of a wake-up method of a smart device according to an embodiment of the present invention, as shown in fig. 3, the method may include, but is not limited to, the following steps:
step S301: detecting a voice signal of a user in a target scene;
step S302: carrying out echo cancellation operation and/or noise cancellation operation on the voice signal to obtain a wake-up signal;
step S303: performing awakening judgment (AGC) on the awakening signal;
step S304: judging whether each device is successfully awakened;
step S305: executing the process of carrying out awakening judgment according to the angle and the energy for the intelligent equipment allowed to be awakened;
step S306: and determining that the target equipment responds to the voice signal according to the result of the judgment process.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Fig. 4 is a block diagram of a wake-up apparatus of a smart device according to an embodiment of the present invention; as shown in fig. 4, includes:
an obtaining module 42, configured to obtain, as candidate devices, smart devices that are allowed to be woken up by a wake-up signal from among a plurality of smart devices, where the plurality of smart devices are devices that detect the wake-up signal in a target scene;
a first determining module 44, configured to determine, if the number of the candidate devices is multiple, a target wake-up angle and a target wake-up energy corresponding to each candidate device in the multiple candidate devices, where the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used to indicate an energy at which the wake-up signal is received by each candidate device;
a second determining module 46, configured to determine a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, where the target device is configured to respond to the wake-up signal.
Through the embodiment, when the device which detects the wake-up signal in the target scene is a plurality of intelligent devices, the intelligent devices which are allowed to be woken up by the wake-up signal are obtained as the candidate devices, when the number of the candidate devices is a plurality, the target wake-up angle and the target wake-up energy corresponding to each candidate device are determined, the target device used for responding to the wake-up signal is determined according to the target wake-up angle and the target wake-up energy, and the candidate device with the maximum target wake-up energy is determined as the target device. By adopting the technical scheme, the problems that in the related technology, the accuracy of the intelligent equipment for responding to the awakening instruction is low and the like are solved, and the technical effect of improving the accuracy of the intelligent equipment for responding to the awakening instruction is achieved.
In an exemplary embodiment, the second determining module is configured to determine, as the target device, a candidate device whose target wake-up angle falls within an angle range; and when the target awakening angles corresponding to the candidate devices do not fall into the angle range, determining the candidate device with the maximum target awakening energy as the target device.
In an exemplary embodiment, the first determining module includes: a construction unit, configured to construct a search function of the wake-up angle variable of each candidate device based on the wake-up signal and the wake-up angle variable of each candidate device; and the searching unit is used for carrying out optimization searching on the searching function to obtain the optimal solution of the awakening angle variable of each candidate device as the target awakening angle corresponding to each candidate device.
In an exemplary embodiment, the building unit is further configured to: constructing a covariance matrix of wake-up angle variables for each candidate device based on the wake-up signals; constructing a direction derivative of the wake-up angle variable of each candidate device based on the wake-up angle variable of each candidate device; constructing a maximum likelihood function of a wake-up angle variable of the each candidate device as the search function based on the covariance matrix and the direction vector.
In an exemplary embodiment, the search unit is further configured to: initializing search parameters in an optimized search algorithm to obtain target search parameters, wherein the search parameters comprise: the number of particles, the positions of the particles, the number of iterations, the position range of each particle, the maximum speed of each particle and a learning factor; and executing the optimized search algorithm on the search function by adopting the target search parameter and the linear decreasing inertial weight to obtain an optimal solution of the wake-up angle variable of each candidate device as a target wake-up angle corresponding to each candidate device.
In an exemplary embodiment, the search unit is further configured to: initializing the number of particles, the iteration times, the maximum speed of each particle and the learning factor to obtain a target particle number, a target iteration time, a target maximum speed and a target learning factor, wherein the target particle number, the target iteration time, the target maximum speed and the target learning factor are used for enabling the calculation amount of the optimized search algorithm to be minimum when the accuracy of the optimized search algorithm reaches an accuracy threshold; initializing the position range of each particle according to the microphone array arrangement mode of each candidate device to obtain a target position range; initializing the particle position by using a historical optimal solution to obtain a target particle position, wherein the target search parameter comprises: the target particle number, the target iteration number, the target maximum speed, the target learning factor, the target position range and the target particle position.
In an exemplary embodiment, the first determining module includes: a calculating unit, configured to calculate a sum of energies of the candidate devices in a frequency range of the wake-up signal; a determining unit, configured to determine the energy sum as a target wake-up energy corresponding to each candidate device.
In an exemplary embodiment, the obtaining module includes: an execution module, configured to perform an echo cancellation operation and/or a noise cancellation operation on a voice signal received by each smart device to obtain the wake-up signal, where the noise cancellation operation includes at least one of: stationary noise suppression, reverberation suppression, non-stationary noise suppression; the judging module is used for judging the awakening of each intelligent device based on the awakening signal; a fourth determining module, configured to determine, as the candidate device, a smart device that is successfully awakened and distinguished from the plurality of smart devices.
An embodiment of the present invention further provides a storage medium including a stored program, wherein the program executes any one of the methods described above.
Alternatively, in the present embodiment, the storage medium may be configured to store program codes for performing the following steps:
s1, acquiring intelligent devices which are allowed to be awakened by an awakening signal from a plurality of intelligent devices as candidate devices, wherein the intelligent devices are the devices which detect the awakening signal in the target scene;
s2, determining, when the number of the candidate devices is multiple, a target wake-up angle and a target wake-up energy corresponding to each candidate device in the multiple candidate devices, where the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used to indicate an energy of the wake-up signal received by each candidate device;
s3, determining a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is configured to respond to the wake-up signal.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring intelligent devices which are allowed to be awakened by an awakening signal from a plurality of intelligent devices as candidate devices, wherein the intelligent devices are the devices which detect the awakening signal in the target scene;
s2, determining, when the number of the candidate devices is multiple, a target wake-up angle and a target wake-up energy corresponding to each candidate device in the multiple candidate devices, where the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used to indicate an energy of the wake-up signal received by each candidate device;
s3, determining a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is configured to respond to the wake-up signal.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A method for waking up an intelligent device, comprising:
acquiring a smart device which is allowed to be awakened by an awakening signal from a plurality of smart devices as candidate devices, wherein the plurality of smart devices are devices which detect the awakening signal in a target scene;
determining a target wake-up angle and a target wake-up energy corresponding to each candidate device in the plurality of candidate devices when the number of the candidate devices is multiple, wherein the target wake-up angle is used for indicating a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used for indicating an energy of the wake-up signal received by each candidate device;
and determining a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is used for responding to the wake-up signal.
2. The method according to claim 1, wherein the determining a target device from the plurality of candidate devices according to the target wake-up angle and the target wake-up energy comprises:
determining candidate equipment with a target awakening angle falling into an angle range as the target equipment;
and when the target awakening angles corresponding to the candidate devices do not fall into the angle range, determining the candidate device with the maximum target awakening energy as the target device.
3. The method according to claim 1 or 2, wherein the determining a target wake-up angle corresponding to each candidate device of the plurality of candidate devices comprises:
constructing a search function of the wake-up angle variable of each candidate device based on the wake-up signal and the wake-up angle variable of each candidate device;
and carrying out optimization search on the search function to obtain an optimal solution of the awakening angle variable of each candidate device as a target awakening angle corresponding to each candidate device.
4. The smart device wake-up method according to claim 3, wherein the constructing a search function of the wake-up angle variable of each candidate device based on the wake-up signal and the wake-up angle variable of each candidate device comprises:
constructing a covariance matrix of wake-up angle variables for each candidate device based on the wake-up signals;
constructing a direction derivative of the wake-up angle variable of each candidate device based on the wake-up angle variable of each candidate device;
constructing a maximum likelihood function of a wake-up angle variable of the each candidate device as the search function based on the covariance matrix and the direction vector.
5. The method for waking up an intelligent device according to claim 3 or 4, wherein the performing an optimized search on the search function to obtain an optimal solution of the wake-up angle variable of each candidate device as the target wake-up angle corresponding to each candidate device includes:
initializing search parameters in an optimized search algorithm to obtain target search parameters, wherein the search parameters comprise: the number of particles, the positions of the particles, the number of iterations, the position range of each particle, the maximum speed of each particle and a learning factor;
and executing the optimized search algorithm on the search function by adopting the target search parameter and the linear decreasing inertial weight to obtain an optimal solution of the wake-up angle variable of each candidate device as a target wake-up angle corresponding to each candidate device.
6. The method for waking up an intelligent device according to claim 5, wherein initializing the search parameter in the optimized search algorithm to obtain the target search parameter comprises:
initializing the number of particles, the iteration times, the maximum speed of each particle and the learning factor to obtain a target particle number, a target iteration time, a target maximum speed and a target learning factor, wherein the target particle number, the target iteration time, the target maximum speed and the target learning factor are used for enabling the calculation amount of the optimized search algorithm to be minimum when the accuracy of the optimized search algorithm reaches an accuracy threshold;
initializing the position range of each particle according to the microphone array arrangement mode of each candidate device to obtain a target position range;
initializing the particle position by using a historical optimal solution to obtain a target particle position, wherein the target search parameter comprises: the target particle number, the target iteration number, the target maximum speed, the target learning factor, the target position range and the target particle position.
7. The method of claim 1, wherein the determining the target wake-up energy for each of the plurality of candidate devices comprises:
calculating the energy sum of each candidate device in the frequency range of the wake-up signal;
and determining the energy sum as a target wake-up energy corresponding to each candidate device.
8. The method for waking up a smart device according to claim 1, wherein the obtaining, as the candidate device, the smart device that is allowed to wake up by the wake-up signal from among the plurality of smart devices comprises:
performing echo cancellation operation and/or noise cancellation operation on the voice signal received by each intelligent device to obtain the wake-up signal, wherein the noise cancellation operation includes at least one of the following operations: stationary noise suppression, reverberation suppression, non-stationary noise suppression;
performing awakening judgment on each intelligent device based on the awakening signal;
and determining the intelligent equipment which is successfully awakened and distinguished in the plurality of intelligent equipment as the candidate equipment.
9. A wake-up unit of a smart device, comprising:
the device comprises an acquisition module, a judgment module and a control module, wherein the acquisition module is used for acquiring intelligent devices which are allowed to be awakened by an awakening signal from a plurality of intelligent devices as candidate devices, and the intelligent devices are devices which detect the awakening signal in a target scene;
a first determining module, configured to determine, when the number of the candidate devices is multiple, a target wake-up angle and a target wake-up energy corresponding to each candidate device in the multiple candidate devices, where the target wake-up angle is used to indicate a direction of an audio source position of the wake-up signal relative to each candidate device, and the target wake-up energy is used to indicate an energy at which the wake-up signal is received by each candidate device;
a second determining module, configured to determine a target device from the candidate devices according to the target wake-up angle and the target wake-up energy, where the target device is configured to respond to the wake-up signal.
10. A computer-readable storage medium, comprising a stored program, wherein the program is operable to perform the method of any one of claims 1 to 8.
11. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 8 by means of the computer program.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110725401.3A CN113593548B (en) | 2021-06-29 | 2021-06-29 | Method and device for waking up intelligent equipment, storage medium and electronic device |
| PCT/CN2022/095732 WO2023273747A1 (en) | 2021-06-29 | 2022-05-27 | Wake-up method and apparatus for smart device, storage medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110725401.3A CN113593548B (en) | 2021-06-29 | 2021-06-29 | Method and device for waking up intelligent equipment, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113593548A true CN113593548A (en) | 2021-11-02 |
| CN113593548B CN113593548B (en) | 2023-12-19 |
Family
ID=78244907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110725401.3A Active CN113593548B (en) | 2021-06-29 | 2021-06-29 | Method and device for waking up intelligent equipment, storage medium and electronic device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113593548B (en) |
| WO (1) | WO2023273747A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023273747A1 (en) * | 2021-06-29 | 2023-01-05 | 青岛海尔科技有限公司 | Wake-up method and apparatus for smart device, storage medium, and electronic device |
| WO2023231552A1 (en) * | 2022-05-30 | 2023-12-07 | 青岛海尔科技有限公司 | Distributed voice wake-up method and apparatus, storage medium, and electronic apparatus |
| WO2023245700A1 (en) * | 2022-06-20 | 2023-12-28 | 青岛海尔科技有限公司 | Audio energy analysis method and related apparatus |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110927668A (en) * | 2019-11-21 | 2020-03-27 | 山东科技大学 | Sound source positioning optimization method of cube microphone array based on particle swarm |
| CN111308414A (en) * | 2019-11-28 | 2020-06-19 | 深圳大学 | Method and system for estimating direction of arrival, intelligent terminal and storage medium |
| CN112037789A (en) * | 2020-08-07 | 2020-12-04 | 海尔优家智能科技（北京）有限公司 | Equipment awakening method and device, storage medium and electronic device |
| US20200395005A1 (en) * | 2018-08-06 | 2020-12-17 | Tencent Technology (Shenzhen) Company Limited | Azimuth estimation method, device, and storage medium |
| CN112420051A (en) * | 2020-11-18 | 2021-02-26 | 青岛海尔科技有限公司 | Equipment determination method, device and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109391528A (en) * | 2018-08-31 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | Awakening method, device, equipment and the storage medium of speech-sound intelligent equipment |
| CN109215663A (en) * | 2018-10-11 | 2019-01-15 | 北京小米移动软件有限公司 | Equipment awakening method and device |
| CN109688512B (en) * | 2018-12-26 | 2020-12-22 | 北京猎户星空科技有限公司 | Pickup method and device |
| CN110660390B (en) * | 2019-09-17 | 2022-05-03 | 百度在线网络技术（北京）有限公司 | Intelligent device wake-up method, intelligent device and computer readable storage medium |
| CN110740083A (en) * | 2019-10-23 | 2020-01-31 | 广东美的制冷设备有限公司 | Voice equipment awakening method and device, household appliance and readable storage medium |
| CN113593548B (en) * | 2021-06-29 | 2023-12-19 | 青岛海尔科技有限公司 | Method and device for waking up intelligent equipment, storage medium and electronic device |
-
2021
- 2021-06-29 CN CN202110725401.3A patent/CN113593548B/en active Active
-
2022
- 2022-05-27 WO PCT/CN2022/095732 patent/WO2023273747A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200395005A1 (en) * | 2018-08-06 | 2020-12-17 | Tencent Technology (Shenzhen) Company Limited | Azimuth estimation method, device, and storage medium |
| CN110927668A (en) * | 2019-11-21 | 2020-03-27 | 山东科技大学 | Sound source positioning optimization method of cube microphone array based on particle swarm |
| CN111308414A (en) * | 2019-11-28 | 2020-06-19 | 深圳大学 | Method and system for estimating direction of arrival, intelligent terminal and storage medium |
| CN112037789A (en) * | 2020-08-07 | 2020-12-04 | 海尔优家智能科技（北京）有限公司 | Equipment awakening method and device, storage medium and electronic device |
| CN112420051A (en) * | 2020-11-18 | 2021-02-26 | 青岛海尔科技有限公司 | Equipment determination method, device and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023273747A1 (en) * | 2021-06-29 | 2023-01-05 | 青岛海尔科技有限公司 | Wake-up method and apparatus for smart device, storage medium, and electronic device |
| WO2023231552A1 (en) * | 2022-05-30 | 2023-12-07 | 青岛海尔科技有限公司 | Distributed voice wake-up method and apparatus, storage medium, and electronic apparatus |
| WO2023245700A1 (en) * | 2022-06-20 | 2023-12-28 | 青岛海尔科技有限公司 | Audio energy analysis method and related apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023273747A1 (en) | 2023-01-05 |
| CN113593548B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288978B (en) | Speech recognition model training method and device | |
| CN113593548A (en) | Awakening method and device of intelligent equipment, storage medium and electronic device | |
| CN111223497B (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
| CN106910500B (en) | Method and device for voice control of device with microphone array | |
| CN108899044B (en) | Voice signal processing method and device | |
| CN106898348B (en) | Dereverberation control method and device for sound production equipment | |
| CN110600017A (en) | Training method of voice processing model, voice recognition method, system and device | |
| CN108922553B (en) | Direction-of-arrival estimation method and system for sound box equipment | |
| CN110265020B (en) | Voice wake-up method and device, electronic equipment and storage medium | |
| Dorfan et al. | Tree-based recursive expectation-maximization algorithm for localization of acoustic sources | |
| CN112037789A (en) | Equipment awakening method and device, storage medium and electronic device | |
| JP2014142627A (en) | Voice identification method and device | |
| WO2020048431A1 (en) | Voice processing method, electronic device and display device | |
| CN111964226B (en) | Air conditioner control method and device and air conditioner | |
| CN110261816A (en) | Voice Wave arrival direction estimating method and device | |
| CN110930987B (en) | Audio processing method, device and storage medium | |
| CN111862951A (en) | Voice endpoint detection method and device, storage medium and electronic equipment | |
| CN110767225A (en) | Voice interaction method, device and system | |
| WO2024027246A1 (en) | Sound signal processing method and apparatus, and electronic device and storage medium | |
| CN112420051A (en) | Equipment determination method, device and storage medium | |
| CN113488031B (en) | Method and device for determining electronic equipment, storage medium and electronic device | |
| CN113889116A (en) | Voice information processing method and device, storage medium and electronic device | |
| CN112466305B (en) | Voice control method and device of water dispenser | |
| CN112201239B (en) | Determination method and device of target equipment, storage medium and electronic device | |
| CN113593603A (en) | Audio category determination method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |